Sentiment Analysis made easy
Lingmotif 2 is the result of Project FFI2016-78141-P on Sentiment Analysis funded by the Spanish Ministry of Science and Innovation, developed by the Tecnolengua Group at the University of Málaga.
We aim to obtain high-coverage, high-quality lexical resources for Sentiment Analysis with a friendly interface.
Lingmotif is a web application (https://lingmotif.com) that analyzes input texts from a Sentiment Analysis perspective. Basically, it determines the semantic orientation of a text (whether it is positive or negative, and to what extent), by detecting linguistic expressions of polarity, i.e., positivity or negativity.
Unlike most Sentiment Analysis software, Lingmotif is not “just” a classifier, meaning it doesn’t simply classify an input text as positive or negative, it also offers a rich set of quantitative data, a visualization of the “sentiment profile” of the text(s) (including time series), and a detailed qualitative analysis showing text items that were detected as having some kind of semantic orientation. Lingmotif generates HTML files as output, so they can be viewed and searched using any standard browser.
These features make Lingmotif quite unique and make it useful for a wide range of applications.
Currently, Lingmotif is able to analyze English and Spanish texts
Some of the things you can do with Lingmotif:
- Obtain an objective measure of a text’s semantic orientation (polarity) and sentiment intensity.
- Discover the “sentiment profile” or flow of a text.
- Extract all topics and entities from a set of texts.
- Custom specific-domain (e.g., finance, restaurant reviews, etc.) sentiment analysis with our plugin manager.
- Aspect-based sentiment analysis (ABSA).
- Analyze multiple text files or datasets.
- Generate a positive/negative sentiment wordcloud.
- Find out unusually positive/negative sections of a text.
- Compare the evaluative language of different speakers/authors.
- Study the evolution of a speaker’s/author’s evaluative language.
- Classify large collections of short texts (e.g. tweets) according to their polarity.
- Plot any data set (e.g. a time series) against a Lingmotif series.
You can sign up and try the Basic plan. If you feel Lingmotif could be useful to you, let us know. You can obtain an Academic user plan for free simply by requesting it with an academic email account.
If you use this software for your own work or research, please cite it:
Moreno-Ortiz, A. (2019). Mi opinión cuenta: La expresión del sentimiento en la Red. En Comunicación mediada por ordenador: La lengua, el discurso y la imagen (pp. 38-74). Cátedra.
Moreno-Ortiz, A., Fernández-Cruz, Javier, & Pérez-Hernández, Chantal. (2020). Design and Evaluation of SentiEcon: A fine-grained Economic/Financial Sentiment Lexicon from a Corpus of Business News. Proceedings of the 12th Language Resources and Evaluation ConferenceAt: Marseille, 5067-5074. http://www.lrec-conf.org/proceedings/lrec2020/pdf/2020.lrec-1.623.pdf
Moreno-Ortiz, A., Salles-Bernal, S., & Orrequia-Barea, A. (2019). Design and validation of annotation schemas for aspect-based sentiment analysis in the tourism sector. Information Technology & Tourism, 21(4), 535-557. https://doi.org/10.1007/s40558-019-00155-0
Moreno-Ortiz, A., & Pérez-Hernández, C. (2018). Lingmotif-lex: A Wide-coverage, State-of-the-art Lexicon for Sentiment Analysis. Proceedings of the Eleventh International Conference on Language Resources and Evaluation (LREC 2018), 2653-2659.
Moreno-Ortiz, A., & Pérez-Hernández, C. (2017). Tecnolengua Lingmotif at TASS 2017: Spanish Twitter Dataset Classification Combining Wide-coverage Lexical Resources and Text Features. TASS 2017: Workshop on Semantic Analysis at SEPLN, 35-42. http://ceur-ws.org/Vol-1896/p3_tecnolengua_tass2017.pdf
Moreno-Ortiz, A. (2017). Lingmotif: Sentiment Analysis for the Digital Humanities. Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics, 73-76. http://aclweb.org/anthology/E/E17/E17-3019